Skip to content

Commit 3809d49

Browse files
aaronshanaaronshan
committed
add description
1 parent 026ec82 commit 3809d49

File tree

1 file changed

+123
-5
lines changed

1 file changed

+123
-5
lines changed

‎README.md‎

Lines changed: 123 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,7 @@
1+
#hive-third-functions [![Build Status](https://travis-ci.org/aaronshan/hive-third-functions.svg?branch=master)](https://travis-ci.org/aaronshan/hive-third-functions)
2+
13
## Introduction
2-
My udf functions
4+
some useful hive udf functions
35

46
## Build
57

@@ -8,20 +10,94 @@ cd ${project_home}
810
mvn clean package
911
```
1012

11-
It will generate hive-third-functions-1.0-SNAPSHOT-shaded.jar in target directory.
13+
If you want skip unit tests, please run:
14+
```
15+
cd ${project_home}
16+
mvn clean package -DskipTests
17+
```
18+
19+
It will generate hive-third-functions-${version}-shaded.jar in target directory.
20+
21+
You can also directly download file from [release page](https://github.com/aaronshan/hive-third-functions/releases).
22+
23+
> current lastest version is `2.0.0`
24+
25+
## functions
26+
27+
### 1. string functions
28+
29+
| function| description |
30+
|:--|:--|
31+
|pinyin(string) -> string | convert chinese to pinyin|
32+
|md5(string) -> string | md5 hash|
33+
|sha256(string) -> string |sha256 hash|
34+
35+
### 2. array functions
36+
37+
| function| description |
38+
|:--|:--|
39+
|array_contains(array, value) -> boolean | whether ARRAY contains value or not.|
40+
41+
### 3. date functions
42+
43+
| function| description |
44+
|:--|:--|
45+
|dayofweek(date_string \| date) -> int | day of week,if monday,return 1, sunday return 7, error return null.|
46+
|zodiac_en(date_string \| date) -> string | convert date to zodiac|
47+
|zodiac_cn(date_string \| date) -> string | convert date to zodiac chinese |
48+
|typeofdate(date_string \| date) -> string | for chinese. 获取日期的类型(1: 法定节假日, 2: 正常周末, 3: 正常工作日 4:攒假的工作日),错误返回-1. |
49+
50+
### 4. JSON functions
51+
| function| description |
52+
|:--|:--|
53+
|json_array_get(json, jsonPath) -> array(varchar) |returns the element at the specified index into the `json_array`. The index is zero-based.|
54+
|json_array_length(json, jsonPath) -> array(varchar) |Returns the array length of `json` (a string containing a JSON array).|
55+
|json_array_extract(json, jsonPath) -> array(varchar) |extract json array by given jsonPath.|
56+
|json_array_extract_scalar(json, jsonPath) -> array(varchar) |like `json_array_extract`, but returns the result value as a string (as opposed to being encoded as JSON).|
57+
|json_extract(json, jsonPath) -> array(varchar) |extract json by given jsonPath.|
58+
|json_extract_scalar(json, jsonPath) -> array(varchar) |like `json_extract`, but returns the result value as a string (as opposed to being encoded as JSON).|
59+
|json_size(json, jsonPath) -> array(varchar) |like `json_extract`, but returns the size of the value. For objects or arrays, the size is the number of members, and the size of a scalar value is zero.|
60+
61+
### 5. China Id Card functions
62+
63+
| function| description |
64+
|:--|:--|
65+
|id_card_province(string) -> string |get user's province|
66+
|id_card_city(string) -> string |get user's city|
67+
|id_card_area(string) -> string |get user's area|
68+
|id_card_birthday(string) -> string |get user's birthday|
69+
|id_card_gender(string) -> string |get user's gender|
70+
|is_valid_id_card(string) -> boolean |determine is valid china id card No.|
71+
|id_card_info(string) -> json |get china id card info. include province, city, area etc.|
1272

1373
## Use
1474

1575
Put these statements into ${HOME}/.hiverc or exec its on hive cli env.
1676

1777
```
1878
add jar ${jar_location_dir}/hive-third-functions-1.0-SNAPSHOT-shaded.jar
19-
create temporary function arrayContains as 'cc.shanruifeng.functions.array.UDFArrayContains';
79+
create temporary function array_contains as 'cc.shanruifeng.functions.array.UDFArrayContains';
2080
create temporary function dayOfWeek as 'cc.shanruifeng.functions.date.UDFDayOfWeek';
2181
create temporary function typeOfDay as 'cc.shanruifeng.functions.date.UDFTypeOfDay';
22-
create temporary function zodiacCn as 'cc.shanruifeng.functions.date.UDFZodiacSignCn';
23-
create temporary function zodiacEn as 'cc.shanruifeng.functions.date.UDFZodiacSignEn';
82+
create temporary function zodiac_cn as 'cc.shanruifeng.functions.date.UDFZodiacSignCn';
83+
create temporary function zodiac_en as 'cc.shanruifeng.functions.date.UDFZodiacSignEn';
2484
create temporary function pinyin as 'cc.shanruifeng.functions.string.UDFChineseToPinYin';
85+
create temporary function md5 as 'cc.shanruifeng.functions.string.UDFMd5';
86+
create temporary function sha256 as 'cc.shanruifeng.functions.string.UDFSha256';
87+
create temporary function json_array_get as 'cc.shanruifeng.functions.json.UDFJsonArrayGet';
88+
create temporary function json_array_length as 'cc.shanruifeng.functions.json.UDFJsonArrayLength';
89+
create temporary function json_array_extract as 'cc.shanruifeng.functions.json.UDFJsonArrayExtract';
90+
create temporary function json_array_extract_scalar as 'cc.shanruifeng.functions.json.UDFJsonArrayExtractScalar';
91+
create temporary function json_extract as 'cc.shanruifeng.functions.json.UDFJsonExtract';
92+
create temporary function json_extract_scalar as 'cc.shanruifeng.functions.json.UDFJsonExtractScalar';
93+
create temporary function json_size as 'cc.shanruifeng.functions.json.UDFJsonSize';
94+
create temporary function id_card_province as 'cc.shanruifeng.functions.card.UDFChinaIdCardProvince';
95+
create temporary function id_card_city as 'cc.shanruifeng.functions.card.UDFChinaIdCardCity';
96+
create temporary function id_card_area as 'cc.shanruifeng.functions.card.UDFChinaIdCardArea';
97+
create temporary function id_card_birthday as 'cc.shanruifeng.functions.card.UDFChinaIdCardBirthday';
98+
create temporary function id_card_gender as 'cc.shanruifeng.functions.card.UDFChinaIdCardGender';
99+
create temporary function is_valid_id_card as 'cc.shanruifeng.functions.card.UDFChinaIdCardValid';
100+
create temporary function id_card_info as 'cc.shanruifeng.functions.card.UDFChinaIdCardInfo';
25101
```
26102

27103
You can use these statements on hive cli env get detail of function.
@@ -38,4 +114,46 @@ zodiacCn(date) - from the input date string or separate month and day arguments,
38114
Example:
39115
> select zodiacCn(date_string) from src;
40116
> select zodiacCn(month, day) from src;
117+
```
118+
119+
### example
120+
```
121+
select pinyin('中国') => zhongguo
122+
select md5('aaronshan') => 95686bc0483262afe170b550dd4544d1
123+
select sha256('aaronshan') => d16bb375433ad383169f911afdf45e209eabfcf047ba1faebdd8f6a0b39e0a32
124+
```
125+
126+
```
127+
select dayOfWeek('2016-07-12') => 2
128+
select typeOfDay('2016-10-01') => 1
129+
select typeOfDay('2016-07-16') => 2
130+
select typeOfDay('2016-07-15') => 3
131+
select typeOfDay('2016-09-18') => 4
132+
select zodiac_cn('1989-01-08') => 魔羯座
133+
select zodiac_en('1989-01-08') => Capricorn
134+
```
135+
136+
```
137+
select id_card_info('110101198901084517') => {"area":"东城区","valid":true,"province":"北京市","gender":"男","city":"北京市"}
138+
```
139+
140+
```
141+
select json_array_get("[{\"a\":{\"b\":\"13\"}}, {\"a\":{\"b\":\"18\"}}, {\"a\":{\"b\":\"12\"}}]", 1); => {"a":{"b":"18"}}
142+
select json_array_get('["a", "b", "c"]', 0); => 'a'
143+
select json_array_get('["a", "b", "c"]', 1); => 'b'
144+
select json_array_get('["c", "b", "a"]', -1); => 'a'
145+
select json_array_get('["c", "b", "a"]', -2); => 'b'
146+
select json_array_get('[]', 0); => null
147+
select json_array_get('["a", "b", "c"]', 10); => null
148+
select json_array_get('["c", "b", "a"]', -10); => null
149+
select json_array_length("[{\"a\":{\"b\":\"13\"}}, {\"a\":{\"b\":\"18\"}}, {\"a\":{\"b\":\"12\"}}]"); => 3
150+
select json_array_extract("[{\"a\":{\"b\":\"13\"}}, {\"a\":{\"b\":\"18\"}}, {\"a\":{\"b\":\"12\"}}]", "$.a.b"); => ["\"13\"","\"18\"","\"12\""]
151+
select json_array_extract_scalar("[{\"a\":{\"b\":\"13\"}}, {\"a\":{\"b\":\"18\"}}, {\"a\":{\"b\":\"12\"}}]", "$.a.b") => ["13","18","12"]
152+
select json_extract("{\"a\":{\"b\":\"12\"}}", "$.a.b"); => "12"
153+
select json_extract_scalar("{\"a\":{\"b\":\"12\"}}", "$.a.b") => 12
154+
select json_extract_scalar('[1, 2, 3]', '$[2]');
155+
select json_extract_scalar(json, '$.store.book[0].author');
156+
select json_size('{"x": {"a": 1, "b": 2}}', '$.x'); => 2
157+
select json_size('{"x": [1, 2, 3]}', '$.x'); => 3
158+
select json_size('{"x": {"a": 1, "b": 2}}', '$.x.a'); => 0
41159
```

0 commit comments

Comments
 (0)